Greg Linden has an excellent post about MapReduce and how some database gurus view at as "a giant step backwards". Personally I don't buy it and we're implementing something similar for Hyperix. Here's an excerpt of what Greg had to say.
"The comments on the post are enjoyable and useful. Many rightfully point out that it might not be fair to compare a system like MapReduce to a full database. DeWitt and Stonebraker do partially address this, though, by not just limiting their criticism to GFS, but also going after BigTable.The most compelling part of the post for me is their argument that some algorithms require random access to data, something that is not well supported by GFS, and it is not always easy or efficient to restructure those algorithms primarily to do sequential scans."