If your goal is simply to provide internal users with access to the Internet then this is possible. As long as the link layer protocol supports the exchange of keep-alive messages from router to router, link failure will be detected by the link layer protocol. Floating static routes can then reliably direct all outbound traffic to a working ISP link. Port Address Translation (PAT) is then used to send outbound packets with a source IP address associated by the ISP with that outbound link. Return traffic will automatically come back via the same working link, because that link is the only link servicing that address range.

If this interface connected to ISP1 doesn't go your router will not detect the link failure. In that case you can use the policy based routing with track feature so identify the link being down and second isp will take over.

http://www.cisco.com/en/US/docs/ios/12_3/12_3x/12_3xe/feature/guide/dbackupx.html

Of course, this approach won't work if you're providing services to the outside world, as the addresses associated with the failed link will disappear from the Internet. Similarly, connections established over the link that failed will need to be reconnected. However, for many applications this impact is minor.