I think Internal Fuzzy Match Analysis is the one you want, not cross file repetition. The help explains what this does as follows:
Internal fuzzy match analysis calculates the maximum additional leverage that can be obtained by the translator interactively translating the document with a translation memory. It assumes that the translator will translate the document from start to end, segment by segment. After each segment is confirmed, the translation memory is updated, and the best match applied to the next segment.
So you can do one file at a time if you like and achieve the same thing as you did using Workbench. It's quite interesting to hear you using this feature in Workbench as it was not well known... at least I didn't think it was..!