Parallel Text Searching on a Beowulf Cluster using SRW

I haven't had a chance to read this article. It's in the September issue of D-Lib. They are trying to find a fast, cheap way to search really big databases (50 million records). It's by 3 researchers from OCLC (Ralph R. LeVan, Thomas B. Hickey, and Jenny Toves). In their abstract they say:

The article should be of interest to anyone seeking an inexpensive, open source, text-searching framework that scales to extremely large databases. The technology described uses the SRW (Search/Retrieve Web) service in a manner nearly identical to federated searching in the metasearch community and should be of interest to anyone doing federated searching.