The next step is to run more tests with more hives, and more test groups (with - as suggested elsewhere in the discussion - graduated exposure levels)
Not to run around like a headless chook claiming the preliminary test actually means anything.
1. Do limited unscientific test.
Try couchdb if you want to select ranges.
Its keys are stored in a heap, so selecting ranges of values is a core use case.
The view system also uses the same mechanism, so by having a cached view you can emit any key you like per record, and grab individual or ranges of values.