Web search engines achieve efficient performance by partitioning and replicating the indexing data structure used to support query processing. Current practice simply partitions and replicates the text collection on the set of cluster processors and then constructs in each processor an index data structure. This paper proposes a different approach by constructing an index data structure that properly considers the fact that data is partitioned and replicated. This leads to a so-called 3D indexing strategy that outperforms current approaches. Performance is further boosted by introducing an application caching scheme devised to hold most frequently issued queries.