controlling memory management with regard to a specific query (or groups of connections)

As a temporary fix I need to write some uploaded image files to PostgreSQL until a task server can read/process/delete
them.  

The problem I've run into (via server load tests that model our production environment), is that these read/writes end
uppushing the indexes used by other queries out of memory -- causing them to be re-read from disk.   These files can be
anywherefrom 200k to 5MB. 

has anyone dealt with situations like this before and has any suggestions?  I could use a dedicated db connection if
thatwould introduce any options.