I just wrote a Ruby script that does pretty much the same thing: https://gist.github.com/865841. I used a simple bloom filter for de-duplication. It's a bit overkill. A simple hash on the twitpic_id will probably work just as well if not better.
What's fun about this is it's 100% javascript. No server load :)
True, right now any retweets are shown as duplicates.
Just to add more context, my little site I try to keep up and running: http://view140.com
Pretty neat, but you could maybe sort/filter with specific hashtags ?
heh, I stayed up all night working on one too. Will launch it soon