Process capability for non-normal distribution using Minitab 12

Six sigma training introduces how to analyze process capability on normal distribution data. Firstly, plotting and analyzing data with normal distribution:
state - Basic Statistics - Display Descriptive Statistics
Secondly, six sigma theory distinguishes the fitness of data to suspected distribution by p-value. The test rejects the hypothesis of normality when the p-value is less than or equal to 0.05 (1 possible exception over 20 cases should be considered).
However, read line (calculated normal distribution) is not fitted to our data. Our data is activity time measured in Minute. Time measurement is always larger than 0, and thus our data is obviously not a zero-centered normal distribution.
p-value=0.00 means the null hypothesis, data fit normal distribution, fails as well.

So, question is - <>how to fit our data to other distribution, and find a acceptable p-value larger than 0.05.
After searching the internet and manual for v12, version 12 provide no capability to fit data into non-normal distribution and find related p-value. Version 18 could fit several potential candidates, and calculate corresponding p-value sapaterly[reference: How to Identify the Distribution of Your Data using Minitab].
There is alternative way to do the magic - Box-Cox Transformation for Non-Normal Data [MINITAB User’s Guide 2: Data Analysis and Quality Tools, revision 12 1998, section 12].

The Box-Cox transformation can be used to correct both non-normality in process data.....
Under most conditions, it is not necessary to correct for non-normality unless the data are highly skewed.

MINITAB provides two Box-Cox transformations: ...
First, use the stand-alone command as an exploratory tool to help you determine the best lambda value for the transformation.
Then, when you enter the control chart command, use the transformation option to transform the data at the same time you draw the chart.

So, process capability for my cases is:
1. Find a lambda for data transformation (0.225)
2. use the transformed data to pass p-value test for normal distribution hypothesis.
3. analyze the process capability on transformed data or origin data with lambda.