Fallen30angel,
Well I haven't done this, but I'll take a shot at some ideas for you.
First off are we talking about a manual machine ore a CNC controlled CMM?
If manual, you should be able to conduct the study in the same way as with any other instrument. i.e. 10 parts three operators.
If the machine is CNC you might consider doing a capability study instead of a gage R & R.
Or
You could check the same 10 parts on three different days at different times of the day (environmental changes)
Or
You could have three different people write the program to check the same 10 parts.
Hope this gives you some ideas.
Anyone else out there can help?
James